Microsoft Research debuts Magnetar, a zero-knowledge proving system for ordinary code
In short: Microsoft Research released Magnetar, a zero-knowledge virtual machine (zkVM) capable of generating cryptographic proofs that a program executed correctly, without needing anyone to rerun it or trust the operator. Instead of forcing developers to rewrite applications as custom cryptographic circuits, Magnetar proves standard RISC-V machine code, so programs written in Rust, Go, or C can be compiled normally and proven as-is. Benchmarks across 15 programs show it processing 7.2 to 8.7 million instructions per second on a laptop, with proofs checkable in roughly 12 milliseconds, and its cryptographic security depends only on established hash functions like SHA-256 or SHA-3 rather than elliptic curves or lattice-based schemes.
This summary was generated automatically by AI from Microsoft Research's publication. It is our own text, not a copy of the original — facts, figures and quotes belong to the source, linked above and below.
What changed?
- 1Compiles and proves ordinary Rust, Go, or C programs through RISC-V execution, skipping manual circuit design
- 2Benchmark speed of 7.2-8.7 million proven instructions per second on a laptop (9.5-12.8 million with an optimized version)
- 3Across 15 test programs, outpaces the fastest comparable zkVMs by a factor of 10 to 39 on average, and by over 300x versus two systems on a token-transfer test
- 4Proof verification takes about 12 milliseconds
- 5Relies solely on standard hash functions (SHA-256/SHA-3) instead of elliptic curves, lattices, or a trusted setup
- 6Builds on more than a decade of prior Microsoft Research work, including Spartan, Phalanx, the Nova family, Brakedown, Jolt, and BinarySpartan
Why it matters
Zero-knowledge proofs let any party verify that a computation ran correctly without redoing the work or trusting the operator, which matters for auditing AI agent behavior, verifying compliance, and checking transaction processing without exposing private data. Because Magnetar avoids elliptic curves and lattices, it sidesteps the cryptographic risks posed by future quantum computers while still delivering major speed gains over earlier proving systems, moving the technology closer to practical, everyday use by regular developers rather than cryptography specialists.
Sources
- Microsoft ResearchOfficialPrimary sourceOriginal article →„Proof-based general-purpose computing with Magnetar“15 Oct 2026, 19:00
- Published by source
- 15 Oct 2026, 19:00
- Found by our system
- 15 Oct 2026, 19:11
- Summary generated
- 15 Oct 2026, 19:14
This article was written by AI from the original source. Facts, numbers and prices come from the source; missing values are marked “Not specified”. Legal notice, copyright and privacy